[ViewVC] Diff of: cvs/AnyEvent-HTTP/HTTP.pm

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.43 by root, Mon Jul 6 03:03:12 2009 UTC vs.
Revision 1.74 by root, Fri Dec 31 22:40:54 2010 UTC

…		…
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Errno ();	44	use Errno ();
45		45
46	use AnyEvent 4.452 ();	46	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
50		49
51	use base Exporter::;	50	use base Exporter::;
52		51
53	our $VERSION = '1.12';	52	our $VERSION = '1.5';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
…		…
92	must be an absolute http or https URL.	91	must be an absolute http or https URL.
93		92
94	When called in void context, nothing is returned. In other contexts,	93	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	94	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	95	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	96	destroyed before the callback is called, the request will be cancelled.
98		97
99	The callback will be called with the response body data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if an error occured), and a hash-ref with response headers as	99	(or C<undef> if an error occured), and a hash-ref with response headers
101	second argument.	100	(and trailers) as second argument.
102		101
103	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	105	three parts of the HTTP Status-Line of the same name. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
106	pseudo-header C<URL> contains the original URL (which can differ from the	110	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
108		122
109	If the server sends a header multiple times, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
…		…
136	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
137	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
138		152
139	=item headers => hashref	153	=item headers => hashref
140		154
141	The request headers to use. Currently, C<http_request> may provide its	155	The request headers to use. Currently, C<http_request> may provide its own
142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	156	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
143	and will provide defaults for C<User-Agent:> and C<Referer:>.	157	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
		158	(this can be suppressed by using C<undef> for these headers in which case
		159	they won't be sent at all).
144		160
145	=item timeout => $seconds	161	=item timeout => $seconds
146		162
147	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
148	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
149		168
150	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
151		170
152	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
153	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
154		173
155	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
156	HTTPS.	175	HTTPS.
157		176
158	=item body => $string	177	=item body => $string
159		178
160	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be sent as-is (future versions of
161	this module might offer more options).	180	this module might offer more options).
162		181
163	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
164		183
165	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
166	based on the original netscape specification.	185	based on the original netscape specification.
167		186
168	The C<$hash_ref> must be an (initially empty) hash reference which will	187	The C<$hash_ref> must be an (initially empty) hash reference which will
169	get updated automatically. It is possible to save the cookie_jar to	188	get updated automatically. It is possible to save the cookie jar to
170	persistent storage with something like JSON or Storable, but this is not	189	persistent storage with something like JSON or Storable, but this is not
171	recommended, as expiry times are currently being ignored.	190	recommended, as session-only cookies might survive longer than expected.
172		191
173	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not meant to be complete. If
174	meant to be complete. If you want complete cookie management you have to	193	you want complete cookie management you have to do that on your
175	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	own. C<cookie_jar> is meant as a quick fix to get some cookie-using sites
176	cookie-using sites working. Cookies are a privacy disaster, do not use	195	working. Cookies are a privacy disaster, do not use them unless required
177	them unless required to.	196	to.
		197
		198	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		199	headers will be set and handled by this module, otherwise they will be
		200	left untouched.
178		201
179	=item tls_ctx => $scheme \| $tls_ctx	202	=item tls_ctx => $scheme \| $tls_ctx
180		203
181	Specifies the AnyEvent::TLS context to be used for https connections. This	204	Specifies the AnyEvent::TLS context to be used for https connections. This
182	parameter follows the same rules as the C<tls_ctx> parameter to	205	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
186	verification) TLS context.	209	verification) TLS context.
187		210
188	The default for this option is C<low>, which could be interpreted as "give	211	The default for this option is C<low>, which could be interpreted as "give
189	me the page, no matter what".	212	me the page, no matter what".
190		213
		214	=item on_prepare => $callback->($fh)
		215
		216	In rare cases you need to "tune" the socket before it is used to
		217	connect (for exmaple, to bind it on a given IP address). This parameter
		218	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		219	and behaves exactly the same way (e.g. it has to provide a
		220	timeout). See the description for the C<$prepare_cb> argument of
		221	C<AnyEvent::Socket::tcp_connect> for details.
		222
		223	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		224
		225	In even rarer cases you want total control over how AnyEvent::HTTP
		226	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		227	to do this, but you can provide your own C<tcp_connect> function -
		228	obviously, it has to follow the same calling conventions, except that it
		229	may always return a connection guard object.
		230
		231	There are probably lots of weird uses for this function, starting from
		232	tracing the hosts C<http_request> actually tries to connect, to (inexact
		233	but fast) host => IP address caching or even socks protocol support.
		234
191	=item on_header => $callback->($headers)	235	=item on_header => $callback->($headers)
192		236
193	When specified, this callback will be called with the header hash as soon	237	When specified, this callback will be called with the header hash as soon
194	as headers have been successfully received from the remote server (not on	238	as headers have been successfully received from the remote server (not on
195	locally-generated errors).	239	locally-generated errors).
…		…
200		244
201	This callback is useful, among other things, to quickly reject unwanted	245	This callback is useful, among other things, to quickly reject unwanted
202	content, which, if it is supposed to be rare, can be faster than first	246	content, which, if it is supposed to be rare, can be faster than first
203	doing a C<HEAD> request.	247	doing a C<HEAD> request.
204		248
		249	The downside is that cancelling the request makes it impossible to re-use
		250	the connection. Also, the C<on_header> callback will not receive any
		251	trailer (headers sent after the response body).
		252
205	Example: cancel the request unless the content-type is "text/html".	253	Example: cancel the request unless the content-type is "text/html".
206		254
207	on_header => sub {	255	on_header => sub {
208	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/	256	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
209	},	257	},
…		…
216		264
217	It has to return either true (in which case AnyEvent::HTTP will continue),	265	It has to return either true (in which case AnyEvent::HTTP will continue),
218	or false, in which case AnyEvent::HTTP will cancel the download (and call	266	or false, in which case AnyEvent::HTTP will cancel the download (and call
219	the completion callback with an error code of C<598>).	267	the completion callback with an error code of C<598>).
220		268
		269	The downside to cancelling the request is that it makes it impossible to
		270	re-use the connection.
		271
221	This callback is useful when the data is too large to be held in memory	272	This callback is useful when the data is too large to be held in memory
222	(so the callback writes it to a file) or when only some information should	273	(so the callback writes it to a file) or when only some information should
223	be extracted, or when the body should be processed incrementally.	274	be extracted, or when the body should be processed incrementally.
224		275
225	It is usually preferred over doing your own body handling via	276	It is usually preferred over doing your own body handling via
226	C<want_body_handle>.	277	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		278	only used to create a connection, C<want_body_handle> is the better
		279	alternative, as it allows you to install your own event handler, reducing
		280	resource usage.
227		281
228	=item want_body_handle => $enable	282	=item want_body_handle => $enable
229		283
230	When enabled (default is disabled), the behaviour of AnyEvent::HTTP	284	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
231	changes considerably: after parsing the headers, and instead of	285	changes considerably: after parsing the headers, and instead of
…		…
243	This is useful with some push-type services, where, after the initial	297	This is useful with some push-type services, where, after the initial
244	headers, an interactive protocol is used (typical example would be the	298	headers, an interactive protocol is used (typical example would be the
245	push-style twitter API which starts a JSON/XML stream).	299	push-style twitter API which starts a JSON/XML stream).
246		300
247	If you think you need this, first have a look at C<on_body>, to see if	301	If you think you need this, first have a look at C<on_body>, to see if
248	that doesn'T solve your problem in a better way.	302	that doesn't solve your problem in a better way.
249		303
250	=back	304	=back
251		305
252	Example: make a simple HTTP GET request for http://www.nethype.de/	306	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		307	the response body.
253		308
254	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
255	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
256	print "$body\n";	311	print "$body\n";
257	};	312	};
258		313
259	Example: make a HTTP HEAD request on https://www.google.com/, use a	314	Example: do a HTTP HEAD request on https://www.google.com/, use a
260	timeout of 30 seconds.	315	timeout of 30 seconds.
261		316
262	http_request	317	http_request
263	GET => "https://www.google.com",	318	GET => "https://www.google.com",
264	timeout => 30,	319	timeout => 30,
…		…
267	use Data::Dumper;	322	use Data::Dumper;
268	print Dumper $hdr;	323	print Dumper $hdr;
269	}	324	}
270	;	325	;
271		326
272	Example: make another simple HTTP GET request, but immediately try to	327	Example: do another simple HTTP GET request, but immediately try to
273	cancel it.	328	cancel it.
274		329
275	my $request = http_request GET => "http://www.nethype.de/", sub {	330	my $request = http_request GET => "http://www.nethype.de/", sub {
276	my ($body, $hdr) = @_;	331	my ($body, $hdr) = @_;
277	print "$body\n";	332	print "$body\n";
…		…
309	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
310		365
311	_slot_schedule $_[0];	366	_slot_schedule $_[0];
312	}	367	}
313		368
314	our $qr_nl = qr<\015?\012>;	369	# extract cookies from jar
315	our $qr_nlnl = qr<\015?\012\015?\012>;	370	sub cookie_jar_extract($$$$) {
		371	my ($jar, $uscheme, $uhost, $upath) = @_;
		372
		373	%$jar = () if $jar->{version} != 1;
		374
		375	my @cookies;
		376
		377	while (my ($chost, $paths) = each %$jar) {
		378	next unless ref $paths;
		379
		380	if ($chost =~ /^\./) {
		381	next unless $chost eq substr $uhost, -length $chost;
		382	} elsif ($chost =~ /\./) {
		383	next unless $chost eq $uhost;
		384	} else {
		385	next;
		386	}
		387
		388	while (my ($cpath, $cookies) = each %$paths) {
		389	next unless $cpath eq substr $upath, 0, length $cpath;
		390
		391	while (my ($cookie, $kv) = each %$cookies) {
		392	next if $uscheme ne "https" && exists $kv->{secure};
		393
		394	if (exists $kv->{expires}) {
		395	if (AE::now > parse_date ($kv->{expires})) {
		396	delete $cookies->{$cookie};
		397	next;
		398	}
		399	}
		400
		401	my $value = $kv->{value};
		402
		403	if ($value =~ /[=;,[:space:]]/) {
		404	$value =~ s/([\\"])/\\$1/g;
		405	$value = "\"$value\"";
		406	}
		407
		408	push @cookies, "$cookie=$value";
		409	}
		410	}
		411	}
		412
		413	\@cookies
		414	}
		415
		416	# parse set_cookie header into jar
		417	sub cookie_jar_set_cookie($$$) {
		418	my ($jar, $set_cookie, $uhost) = @_;
		419
		420	for ($set_cookie) {
		421	# parse NAME=VALUE
		422	my @kv;
		423
		424	while (
		425	m{
		426	\G\s*
		427	(?:
		428	expires \s=\s ([A-Z][a-z][a-z],\ [^,;]+)
		429	\| ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )
		430	)
		431	}gcxsi
		432	) {
		433	my $name = $2;
		434	my $value = $4;
		435
		436	unless (defined $name) {
		437	# expires
		438	$name = "expires";
		439	$value = $1;
		440	} elsif (!defined $value) {
		441	# quoted
		442	$value = $3;
		443	$value =~ s/\\(.)/$1/gs;
		444	}
		445
		446	push @kv, lc $name, $value;
		447
		448	last unless /\G\s*;/gc;
		449	}
		450
		451	last unless @kv;
		452
		453	my $name = shift @kv;
		454	my %kv = (value => shift @kv, @kv);
		455
		456	$kv{expires} \|\|= format_date (AE::now + $kv{"max-age"})
		457	if exists $kv{"max-age"};
		458
		459	my $cdom;
		460	my $cpath = (delete $kv{path}) \|\| "/";
		461
		462	if (exists $kv{domain}) {
		463	$cdom = delete $kv{domain};
		464
		465	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		466
		467	next if $cdom =~ /\.$/;
		468
		469	# this is not rfc-like and not netscape-like. go figure.
		470	my $ndots = $cdom =~ y/.//;
		471	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		472	} else {
		473	$cdom = $uhost;
		474	}
		475
		476	# store it
		477	$jar->{version} = 1;
		478	$jar->{$cdom}{$cpath}{$name} = \%kv;
		479
		480	redo if /\G\s*,/gc;
		481	}
		482	}
		483
		484	# continue to parse $_ for headers and place them into the arg
		485	sub parse_hdr() {
		486	my %hdr;
		487
		488	# things seen, not parsed:
		489	# p3pP="NON CUR OTPi OUR NOR UNI"
		490
		491	$hdr{lc $1} .= ",$2"
		492	while /\G
		493	([^:\000-\037]*):
		494	[\011\040]*
		495	((?: [^\012]+ \| \012[\011\040] )*)
		496	\012
		497	/gxc;
		498
		499	/\G$/
		500	or return;
		501
		502	# remove the "," prefix we added to all headers above
		503	substr $_, 0, 1, ""
		504	for values %hdr;
		505
		506	\%hdr
		507	}
		508
		509	our $qr_nlnl = qr{(?<![^\012])\015?\012};
316		510
317	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	511	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
318	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	512	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
319		513
320	sub http_request($$@) {	514	sub http_request($$@) {
…		…
332	while (my ($k, $v) = each %$hdr) {	526	while (my ($k, $v) = each %$hdr) {
333	$hdr{lc $k} = $v;	527	$hdr{lc $k} = $v;
334	}	528	}
335	}	529	}
336		530
		531	# pseudo headers for all subsequent responses
		532	my @pseudo = (URL => $url);
		533	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		534
337	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	535	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
338		536
339	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	537	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
340	if $recurse < 0;	538	if $recurse < 0;
341		539
342	my $proxy = $arg{proxy} \|\| $PROXY;	540	my $proxy = $arg{proxy} \|\| $PROXY;
343	my $timeout = $arg{timeout} \|\| $TIMEOUT;	541	my $timeout = $arg{timeout} \|\| $TIMEOUT;
344		542
345	my ($uscheme, $uauthority, $upath, $query, $fragment) =	543	my ($uscheme, $uauthority, $upath, $query, $fragment) =
346	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	544	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
347		545
348	$uscheme = lc $uscheme;	546	$uscheme = lc $uscheme;
349		547
350	my $uport = $uscheme eq "http" ? 80	548	my $uport = $uscheme eq "http" ? 80
351	: $uscheme eq "https" ? 443	549	: $uscheme eq "https" ? 443
352	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });	550	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
353		551
354	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	552	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
355	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	553	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
356		554
357	my $uhost = $1;	555	my $uhost = $1;
358	$uport = $2 if defined $2;	556	$uport = $2 if defined $2;
359		557
360	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";	558	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		559	unless exists $hdr{host};
361		560
362	$uhost =~ s/^\[(.*)\]$/$1/;	561	$uhost =~ s/^\[(.*)\]$/$1/;
363	$upath .= "?$query" if length $query;	562	$upath .= $query if length $query;
364		563
365	$upath =~ s%^/?%/%;	564	$upath =~ s%^/?%/%;
366		565
367	# cookie processing	566	# cookie processing
368	if (my $jar = $arg{cookie_jar}) {	567	if (my $jar = $arg{cookie_jar}) {
369	%$jar = () if $jar->{version} != 1;	568	my $cookies = cookie_jar_extract $jar, $uscheme, $uhost, $upath;
370		569
371	my @cookie;
372
373	while (my ($chost, $v) = each %$jar) {
374	if ($chost =~ /^\./) {
375	next unless $chost eq substr $uhost, -length $chost;
376	} elsif ($chost =~ /\./) {
377	next unless $chost eq $uhost;
378	} else {
379	next;
380	}
381
382	while (my ($cpath, $v) = each %$v) {
383	next unless $cpath eq substr $upath, 0, length $cpath;
384
385	while (my ($k, $v) = each %$v) {
386	next if $uscheme ne "https" && exists $v->{secure};
387	my $value = $v->{value};
388	$value =~ s/([\\"])/\\$1/g;
389	push @cookie, "$k=\"$value\"";
390	}
391	}
392	}
393
394	$hdr{cookie} = join "; ", @cookie	570	$hdr{cookie} = join "; ", @$cookies
395	if @cookie;	571	if @$cookies;
396	}	572	}
397		573
398	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	574	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
399		575
400	if ($proxy) {	576	if ($proxy) {
401	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	577	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
		578
		579	$rscheme = "http" unless defined $rscheme;
402		580
403	# don't support https requests over https-proxy transport,	581	# don't support https requests over https-proxy transport,
404	# can't be done with tls as spec'ed, unless you double-encrypt.	582	# can't be done with tls as spec'ed, unless you double-encrypt.
405	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	583	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
406	} else {	584	} else {
407	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	585	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
408	}	586	}
409		587
410	$hdr{"user-agent"} \|\|= $USERAGENT;	588	# leave out fragment and query string, just a heuristic
411	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic	589	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		590	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
412		591
413	$hdr{"content-length"} = length $arg{body};	592	$hdr{"content-length"} = length $arg{body}
		593	if length $arg{body} \|\| $method ne "GET";
		594
		595	$hdr{connection} = "close TE"; #1.1
		596	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
414		597
415	my %state = (connect_guard => 1);	598	my %state = (connect_guard => 1);
416		599
417	_get_slot $uhost, sub {	600	_get_slot $uhost, sub {
418	$state{slot_guard} = shift;	601	$state{slot_guard} = shift;
419		602
420	return unless $state{connect_guard};	603	return unless $state{connect_guard};
421		604
422	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	605	my $connect_cb = sub {
423	$state{fh} = shift	606	$state{fh} = shift
424	or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url }));	607	or do {
		608	my $err = "$!";
		609	%state = ();
		610	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		611	};
		612
425	pop; # free memory, save a tree	613	pop; # free memory, save a tree
426		614
427	return unless delete $state{connect_guard};	615	return unless delete $state{connect_guard};
428		616
429	# get handle	617	# get handle
430	$state{handle} = new AnyEvent::Handle	618	$state{handle} = new AnyEvent::Handle
431	fh => $state{fh},	619	fh => $state{fh},
		620	peername => $rhost,
		621	tls_ctx => $arg{tls_ctx},
		622	# these need to be reconfigured on keepalive handles
432	timeout => $timeout,	623	timeout => $timeout,
433	peername => $rhost,	624	on_error => sub {
434	tls_ctx => $arg{tls_ctx};	625	%state = ();
		626	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		627	},
		628	on_eof => sub {
		629	%state = ();
		630	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		631	},
		632	;
435		633
436	# limit the number of persistent connections	634	# limit the number of persistent connections
437	# keepalive not yet supported	635	# keepalive not yet supported
438	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	636	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
439	++$KA_COUNT{$_[1]};	637	# ++$KA_COUNT{$_[1]};
440	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	638	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
441	--$KA_COUNT{$_[1]}	639	# --$KA_COUNT{$_[1]}
442	};	640	# };
443	$hdr{connection} = "keep-alive";	641	# $hdr{connection} = "keep-alive";
444	} else {
445	delete $hdr{connection};
446	}	642	# }
447
448	# (re-)configure handle
449	$state{handle}->on_error (sub {
450	%state = ();
451	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
452	});
453	$state{handle}->on_eof (sub {
454	%state = ();
455	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
456	});
457		643
458	$state{handle}->starttls ("connect") if $rscheme eq "https";	644	$state{handle}->starttls ("connect") if $rscheme eq "https";
459		645
460	# handle actual, non-tunneled, request	646	# handle actual, non-tunneled, request
461	my $handle_actual_request = sub {	647	my $handle_actual_request = sub {
462	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	648	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
463		649
464	# send request	650	# send request
465	$state{handle}->push_write (	651	$state{handle}->push_write (
466	"$method $rpath HTTP/1.0\015\012"	652	"$method $rpath HTTP/1.1\015\012"
467	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	653	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
468	. "\015\012"	654	. "\015\012"
469	. (delete $arg{body})	655	. (delete $arg{body})
470	);	656	);
471		657
		658	# return if error occured during push_write()
		659	return unless %state;
		660
472	%hdr = (); # reduce memory usage, save a kitten	661	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
473		662
474	# status line	663	# status line and headers
475	$state{handle}->push_read (line => $qr_nl, sub {	664	$state{read_response} = sub {
476	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
477	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
478
479	my %hdr = ( # response headers
480	HTTPVersion => ",$1",
481	Status => ",$2",
482	Reason => ",$3",
483	URL => ",$url"
484	);
485
486	# headers, could be optimized a bit
487	$state{handle}->unshift_read (line => $qr_nlnl, sub {
488	for ("$_[1]\012") {	665	for ("$_[1]") {
489	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	666	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
490		667
491	# things seen, not parsed:	668	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
492	# p3pP="NON CUR OTPi OUR NOR UNI"	669	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
493		670
494	$hdr{lc $1} .= ",$2"	671	# 100 Continue handling
495	while /\G	672	# should not happen as we don't send expect: 100-continue,
496	([^:\000-\037]*):	673	# but we handle it just in case.
497	[\011\040]*	674	# since we send the request body regardless, if we get an error
498	((?: [^\012]+ \| \012[\011\040] )*)	675	# we are out of-sync, which we currently do NOT handle correctly.
499	\012	676	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
500	/gxc;	677	if $2 eq 100;
501		678
		679	push @pseudo,
		680	HTTPVersion => $1,
		681	Status => $2,
		682	Reason => $3,
502	/\G$/	683	;
		684
		685	my $hdr = parse_hdr
503	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));	686	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		687
		688	%hdr = (%$hdr, @pseudo);
		689	}
		690
		691	# redirect handling
		692	# microsoft and other shitheads don't give a shit for following standards,
		693	# try to support some common forms of broken Location headers.
		694	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		695	$hdr{location} =~ s/^\.\/+//;
		696
		697	my $url = "$rscheme://$uhost:$uport";
		698
		699	unless ($hdr{location} =~ s/^\///) {
		700	$url .= $upath;
		701	$url =~ s/\/[^\/]*$//;
504	}	702	}
505		703
506	substr $_, 0, 1, ""	704	$hdr{location} = "$url/$hdr{location}";
507	for values %hdr;	705	}
508		706
		707	my $redirect;
		708
		709	if ($recurse) {
		710	my $status = $hdr{Status};
		711
		712	# industry standard is to redirect POST as GET for
		713	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		714	# also, the UA should ask the user for 301 and 307 and POST,
		715	# industry standard seems to be to simply follow.
		716	# we go with the industry standard.
		717	if ($status == 301 or $status == 302 or $status == 303) {
		718	# HTTP/1.1 is unclear on how to mutate the method
		719	$method = "GET" unless $method eq "HEAD";
509	# redirect handling	720	$redirect = 1;
510	# microsoft and other shitheads don't give a shit for following standards,	721	} elsif ($status == 307) {
511	# try to support some common forms of broken Location headers.	722	$redirect = 1;
512	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	723	}
513	$hdr{location} =~ s/^\.\/+//;	724	}
514		725
515	my $url = "$rscheme://$uhost:$uport";	726	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		727	my $may_keep_alive = $_[3];
516		728
517	unless ($hdr{location} =~ s/^\///) {	729	$state{handle}->destroy if $state{handle};
		730	%state = ();
		731
		732	if (defined $_[1]) {
		733	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		734	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		735	}
		736
		737	# set-cookie processing
		738	if ($arg{cookie_jar}) {
		739	cookie_jar_set_cookie $arg{cookie_jar}, $hdr{"set-cookie"}, $uhost;
		740	}
		741
		742	if ($redirect && exists $hdr{location}) {
		743	# we ignore any errors, as it is very common to receive
		744	# Content-Length != 0 but no actual body
		745	# we also access %hdr, as $_[1] might be an erro
		746	http_request (
		747	$method => $hdr{location},
		748	%arg,
		749	recurse => $recurse - 1,
		750	Redirect => [$_[0], \%hdr],
		751	$cb);
		752	} else {
		753	$cb->($_[0], \%hdr);
		754	}
		755	};
		756
		757	my $len = $hdr{"content-length"};
		758
		759	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		760	$finish->(undef, 598 => "Request cancelled by on_header");
		761	} elsif (
		762	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		763	or $method eq "HEAD"
		764	or (defined $len && !$len)
		765	) {
		766	# no body
		767	$finish->("", undef, undef, 1);
		768	} else {
		769	# body handling, many different code paths
		770	# - no body expected
		771	# - want_body_handle
		772	# - te chunked
		773	# - 2x length known (with or without on_body)
		774	# - 2x length not known (with or without on_body)
		775	if (!$redirect && $arg{want_body_handle}) {
		776	$_[0]->on_eof (undef);
		777	$_[0]->on_error (undef);
		778	$_[0]->on_read (undef);
		779
		780	$finish->(delete $state{handle});
		781
		782	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		783	my $cl = 0;
		784	my $body = undef;
		785	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		786
		787	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		788
		789	my $read_chunk; $read_chunk = sub {
		790	$_[1] =~ /^([0-9a-fA-F]+)/
		791	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		792
		793	my $len = hex $1;
		794
		795	if ($len) {
518	$url .= $upath;	796	$cl += $len;
519	$url =~ s/\/[^\/]*$//;	797
		798	$_[0]->push_read (chunk => $len, sub {
		799	$on_body->($_[1], \%hdr)
		800	or return $finish->(undef, 598 => "Request cancelled by on_body");
		801
		802	$_[0]->push_read (line => sub {
		803	length $_[1]
		804	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		805	$_[0]->push_read (line => $read_chunk);
		806	});
		807	});
		808	} else {
		809	$hdr{"content-length"} \|\|= $cl;
		810
		811	$_[0]->push_read (line => $qr_nlnl, sub {
		812	if (length $_[1]) {
		813	for ("$_[1]") {
		814	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		815
		816	my $hdr = parse_hdr
		817	or return $finish->(undef, 599 => "Garbled response trailers");
		818
		819	%hdr = (%hdr, %$hdr);
		820	}
		821	}
		822
		823	$finish->($body, undef, undef, 1);
		824	});
		825	}
		826	};
		827
		828	$_[0]->push_read (line => $read_chunk);
		829
		830	} elsif ($arg{on_body}) {
		831	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		832
		833	if ($len) {
		834	$_[0]->on_read (sub {
		835	$len -= length $_[0]{rbuf};
		836
		837	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		838	or return $finish->(undef, 598 => "Request cancelled by on_body");
		839
		840	$len > 0
		841	or $finish->("", undef, undef, 1);
		842	});
		843	} else {
		844	$_[0]->on_eof (sub {
		845	$finish->("");
		846	});
		847	$_[0]->on_read (sub {
		848	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		849	or $finish->(undef, 598 => "Request cancelled by on_body");
		850	});
520	}	851	}
521
522	$hdr{location} = "$url/$hdr{location}";
523	}	852	} else {
		853	$_[0]->on_eof (undef);
524		854
525	my $redirect;
526
527	if ($recurse) {	855	if ($len) {
528	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {	856	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
529	# apparently, mozilla et al. just change POST to GET here	857	$_[0]->on_read (sub {
530	# more research is needed before we do the same	858	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		859	if $len <= length $_[0]{rbuf};
531	$redirect = 1;	860	});
532	} elsif ($hdr{Status} == 303) {	861	} else {
533	# even http/1.1 is unclear on how to mutate the method	862	$_[0]->on_error (sub {
534	$method = "GET" unless $method eq "HEAD";	863	($! == Errno::EPIPE \|\| !$!)
		864	? $finish->(delete $_[0]{rbuf})
		865	: $finish->(undef, 599 => $_[2]);
535	$redirect = 1;	866	});
536	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {	867	$_[0]->on_read (sub { });
537	$redirect = 1;
538	}	868	}
539	}	869	}
540
541	my $finish = sub {
542	$state{handle}->destroy if $state{handle};
543	%state = ();
544
545	# set-cookie processing
546	if ($arg{cookie_jar}) {
547	for ($_[1]{"set-cookie"}) {
548	# parse NAME=VALUE
549	my @kv;
550
551	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
552	my $name = $1;
553	my $value = $3;
554
555	unless ($value) {
556	$value = $2;
557	$value =~ s/\\(.)/$1/gs;
558	}
559
560	push @kv, $name => $value;
561
562	last unless /\G\s*;/gc;
563	}
564
565	last unless @kv;
566
567	my $name = shift @kv;
568	my %kv = (value => shift @kv, @kv);
569
570	my $cdom;
571	my $cpath = (delete $kv{path}) \|\| "/";
572
573	if (exists $kv{domain}) {
574	$cdom = delete $kv{domain};
575
576	$cdom =~ s/^\.?/./; # make sure it starts with a "."
577
578	next if $cdom =~ /\.$/;
579
580	# this is not rfc-like and not netscape-like. go figure.
581	my $ndots = $cdom =~ y/.//;
582	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
583	} else {
584	$cdom = $uhost;
585	}
586
587	# store it
588	$arg{cookie_jar}{version} = 1;
589	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
590
591	redo if /\G\s*,/gc;
592	}
593	}
594
595	if ($redirect) {
596	# we ignore any errors, as it is very common to receive
597	# Content-Length != 0 but no actual body
598	# we also access %hdr, as $_[1] might be an erro
599	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
600	} else {
601	$cb->($_[0], $_[1]);
602	}
603	};
604
605	my $len = $hdr{"content-length"};
606
607	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
608	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
609	} elsif (
610	$hdr{Status} =~ /^(?:1..\|[23]04)$/
611	or $method eq "HEAD"
612	or (defined $len && !$len)
613	) {
614	# no body
615	$finish->("", \%hdr);
616	} else {
617	# body handling, four different code paths
618	# for want_body_handle, on_body (2x), normal (2x)
619	# we might read too much here, but it does not matter yet (no pers. connections)
620	if (!$redirect && $arg{want_body_handle}) {
621	$_[0]->on_eof (undef);
622	$_[0]->on_error (undef);
623	$_[0]->on_read (undef);
624
625	$finish->(delete $state{handle}, \%hdr);
626
627	} elsif ($arg{on_body}) {
628	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
629	if ($len) {
630	$_[0]->on_eof (undef);
631	$_[0]->on_read (sub {
632	$len -= length $_[0]{rbuf};
633
634	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
635	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
636
637	$len > 0
638	or $finish->("", \%hdr);
639	});
640	} else {
641	$_[0]->on_eof (sub {
642	$finish->("", \%hdr);
643	});
644	$_[0]->on_read (sub {
645	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
646	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
647	});
648	}
649	} else {
650	$_[0]->on_eof (undef);
651
652	if ($len) {
653	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
654	$_[0]->on_read (sub {
655	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
656	if $len <= length $_[0]{rbuf};
657	});
658	} else {
659	$_[0]->on_error (sub {
660	$! == Errno::EPIPE \|\| !$!
661	? $finish->(delete $_[0]{rbuf}, \%hdr)
662	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
663	});
664	$_[0]->on_read (sub { });
665	}
666	}
667	}
668	});	870	}
669	});	871	};
		872
		873	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
670	};	874	};
671		875
672	# now handle proxy-CONNECT method	876	# now handle proxy-CONNECT method
673	if ($proxy && $uscheme eq "https") {	877	if ($proxy && $uscheme eq "https") {
674	# oh dear, we have to wrap it into a connect request	878	# oh dear, we have to wrap it into a connect request
675		879
676	# maybe re-use $uauthority with patched port?	880	# maybe re-use $uauthority with patched port?
677	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	881	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
678	$state{handle}->push_read (line => $qr_nlnl, sub {	882	$state{handle}->push_read (line => $qr_nlnl, sub {
679	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	883	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
680	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));	884	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
681		885
682	if ($2 == 200) {	886	if ($2 == 200) {
683	$rpath = $upath;	887	$rpath = $upath;
684	&$handle_actual_request;	888	&$handle_actual_request;
685	} else {	889	} else {
686	%state = ();	890	%state = ();
687	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	891	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
688	}	892	}
689	});	893	});
690	} else {	894	} else {
691	&$handle_actual_request;	895	&$handle_actual_request;
692	}	896	}
693
694	}, sub {
695	$timeout
696	};	897	};
		898
		899	my $tcp_connect = $arg{tcp_connect}
		900	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		901
		902	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		903
697	};	904	};
698		905
699	defined wantarray && AnyEvent::Util::guard { %state = () }	906	defined wantarray && AnyEvent::Util::guard { %state = () }
700	}	907	}
701		908
…		…
715	&http_request	922	&http_request
716	}	923	}
717		924
718	=back	925	=back
719		926
		927	=head2 DNS CACHING
		928
		929	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		930	the actual connection, which in turn uses AnyEvent::DNS to resolve
		931	hostnames. The latter is a simple stub resolver and does no caching
		932	on its own. If you want DNS caching, you currently have to provide
		933	your own default resolver (by storing a suitable resolver object in
		934	C<$AnyEvent::DNS::RESOLVER>).
		935
720	=head2 GLOBAL FUNCTIONS AND VARIABLES	936	=head2 GLOBAL FUNCTIONS AND VARIABLES
721		937
722	=over 4	938	=over 4
723		939
724	=item AnyEvent::HTTP::set_proxy "proxy-url"	940	=item AnyEvent::HTTP::set_proxy "proxy-url"
725		941
726	Sets the default proxy server to use. The proxy-url must begin with a	942	Sets the default proxy server to use. The proxy-url must begin with a
727	string of the form C<http://host:port> (optionally C<https:...>).	943	string of the form C<http://host:port> (optionally C<https:...>), croaks
		944	otherwise.
		945
		946	To clear an already-set proxy, use C<undef>.
		947
		948	=item $date = AnyEvent::HTTP::format_date $timestamp
		949
		950	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		951	Date (RFC 2616).
		952
		953	=item $timestamp = AnyEvent::HTTP::parse_date $date
		954
		955	Takes a HTTP Date (RFC 2616) or a Cookie date (netscape cookie spec) and
		956	returns the corresponding POSIX timestamp, or C<undef> if the date cannot
		957	be parsed.
728		958
729	=item $AnyEvent::HTTP::MAX_RECURSE	959	=item $AnyEvent::HTTP::MAX_RECURSE
730		960
731	The default value for the C<recurse> request parameter (default: C<10>).	961	The default value for the C<recurse> request parameter (default: C<10>).
732		962
…		…
735	The default value for the C<User-Agent> header (the default is	965	The default value for the C<User-Agent> header (the default is
736	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	966	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
737		967
738	=item $AnyEvent::HTTP::MAX_PER_HOST	968	=item $AnyEvent::HTTP::MAX_PER_HOST
739		969
740	The maximum number of concurrent conenctions to the same host (identified	970	The maximum number of concurrent connections to the same host (identified
741	by the hostname). If the limit is exceeded, then the additional requests	971	by the hostname). If the limit is exceeded, then the additional requests
742	are queued until previous connections are closed.	972	are queued until previous connections are closed.
743		973
744	The default value for this is C<4>, and it is highly advisable to not	974	The default value for this is C<4>, and it is highly advisable to not
745	increase it.	975	increase it.
…		…
752		982
753	=back	983	=back
754		984
755	=cut	985	=cut
756		986
		987	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		988	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		989
		990	sub format_date($) {
		991	my ($time) = @_;
		992
		993	# RFC 822/1123 format
		994	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		995
		996	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		997	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		998	$H, $M, $S;
		999	}
		1000
		1001	sub parse_date($) {
		1002	my ($date) = @_;
		1003
		1004	my ($d, $m, $y, $H, $M, $S);
		1005
		1006	if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9])[\- ]([A-Z][a-z][a-z])[\- ]([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		1007	# RFC 822/1123, required by RFC 2616 (with " ")
		1008	# cookie dates (with "-")
		1009
		1010	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		1011
		1012	} elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		1013	# RFC 850
		1014	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		1015
		1016	} elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) {
		1017	# ISO C's asctime
		1018	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		1019	}
		1020	# other formats fail in the loop below
		1021
		1022	for (0..11) {
		1023	if ($m eq $month[$_]) {
		1024	require Time::Local;
		1025	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		1026	}
		1027	}
		1028
		1029	undef
		1030	}
		1031
757	sub set_proxy($) {	1032	sub set_proxy($) {
		1033	if (length $_[0]) {
758	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	1034	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		1035	or Carp::croak "$_[0]: invalid proxy URL";
		1036	$PROXY = [$2, $3 \|\| 3128, $1]
		1037	} else {
		1038	undef $PROXY;
		1039	}
759	}	1040	}
760		1041
761	# initialise proxy from environment	1042	# initialise proxy from environment
		1043	eval {
762	set_proxy $ENV{http_proxy};	1044	set_proxy $ENV{http_proxy};
		1045	};
		1046
		1047	=head2 SOCKS PROXIES
		1048
		1049	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		1050	compile your perl to support socks, or use an external program such as
		1051	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		1052	transparently.
		1053
		1054	Alternatively, for AnyEvent::HTTP only, you can use your own
		1055	C<tcp_connect> function that does the proxy handshake - here is an example
		1056	that works with socks4a proxies:
		1057
		1058	use Errno;
		1059	use AnyEvent::Util;
		1060	use AnyEvent::Socket;
		1061	use AnyEvent::Handle;
		1062
		1063	# host, port and username of/for your socks4a proxy
		1064	my $socks_host = "10.0.0.23";
		1065	my $socks_port = 9050;
		1066	my $socks_user = "";
		1067
		1068	sub socks4a_connect {
		1069	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		1070
		1071	my $hdl = new AnyEvent::Handle
		1072	connect => [$socks_host, $socks_port],
		1073	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1074	on_error => sub { $connect_cb->() },
		1075	;
		1076
		1077	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1078
		1079	$hdl->push_read (chunk => 8, sub {
		1080	my ($hdl, $chunk) = @_;
		1081	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1082
		1083	if ($status == 0x5a) {
		1084	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1085	} else {
		1086	$! = Errno::ENXIO; $connect_cb->();
		1087	}
		1088	});
		1089
		1090	$hdl
		1091	}
		1092
		1093	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1094	possibly after switching off other proxy types:
		1095
		1096	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1097
		1098	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1099	my ($data, $headers) = @_;
		1100	...
		1101	};
763		1102
764	=head1 SEE ALSO	1103	=head1 SEE ALSO
765		1104
766	L<AnyEvent>.	1105	L<AnyEvent>.
767		1106

Diff Legend

-–
+Removed lines
-+
+Added lines
-<
+Changed lines
->
+Changed lines

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.43 by root, Mon Jul 6 03:03:12 2009 UTC vs. Revision 1.74 by root, Fri Dec 31 22:40:54 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.43 by root, Mon Jul 6 03:03:12 2009 UTC vs.
Revision 1.74 by root, Fri Dec 31 22:40:54 2010 UTC